Sébastien Rigaux

Tech watch

← All links

Agent memory

Preserving and retrieving useful context across agent steps or sessions.

GitHub preview card for the rlaope/oh-my-hermes repository, showing the project name, tagline, and counts for contributors, issues, stars, and forks.

oh-my-hermes adds an orchestration layer to Hermes Agent: it maps work categories to models and reasoning effort, loads skills on demand, and can turn a goal into a graph of parallel tasks. Each task keeps a separate write scope, while a distinct node verifies the outcome.

A notable architectural choice is separating preparation from execution evidence: a plan is not treated as completed work, and an agent’s claim that it finished does not validate the result. The project also offers review-gated memory and a dedicated TUI, without replacing or patching Hermes Agent.

rlaope

Tool

Engram: persistent memory for MCP-compatible AI agents

engram.gentlemanprogramming.comPermalink

Engram provides persistent memory for AI agents, compatible with any agent supporting the MCP protocol (Claude Code, Gemini CLI, Codex, VS Code, etc.). The tool runs as a single Go binary with no external dependencies, storing memories in a SQLite file with built-in FTS5 search. It features a TUI, Git sync, and a self-hostable cloud extension, while remaining local-first and open source under the MIT license.

Gentleman-Programming